TrafficBERT: Pre-trained model with large-scale data for long-range traffic flow forecasting
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jin, K. | - |
dc.contributor.author | Wi, J. | - |
dc.contributor.author | Lee, E. | - |
dc.contributor.author | Kang, S. | - |
dc.contributor.author | Kim, S. | - |
dc.contributor.author | Kim, Y. | - |
dc.date.accessioned | 2021-11-11T02:41:07Z | - |
dc.date.available | 2021-11-11T02:41:07Z | - |
dc.date.created | 2021-10-25 | - |
dc.date.issued | 2021-12-30 | - |
dc.identifier.issn | 0957-4174 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/16500 | - |
dc.description.abstract | Traffic flow prediction has various applications such as in traffic systems and autonomous driving. Road conditions have become increasingly complex, and this, in turn, has increased the demand for effective traffic volume predictions. Statistical models and conventional machine-learning models have been employed for this purpose more recently, deep learning has been widely used. However, most deep learning-based models require data additional to traffic information, such as information on adjacent roads or road weather conditions. Therefore, the effectiveness of these models is typically restricted to certain roads. Even if such information were available, there is a possibility of bias toward a specific road. To overcome this limitation, based on the bidirectional encoder representations from transformers (BERT), we propose trafficBERT, a model that is suitable for use on various roads because it is pre-trained with large-scale traffic data. Our model captures time-series information by employing multi-head self-attention in place of the commonly used recurrent neural network. In addition, the autocorrelation between the states before and after each time step is determined more efficiently via factorized embedding parameterization. Our results indicate that trafficBERT outperforms models trained using data for specific roads, as well as commonly used statistical and deep learning models, such as Stacked Autoencoder, and models based on long short-term memory, in terms of accuracy. © 2021 Elsevier Ltd | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Elsevier Ltd | - |
dc.subject | Forecasting | - |
dc.subject | Motor transportation | - |
dc.subject | Recurrent neural networks | - |
dc.subject | Roads and streets | - |
dc.subject | Street traffic control | - |
dc.subject | Autonomous driving | - |
dc.subject | Bidirectional encoder representation from transformer | - |
dc.subject | Large scale data | - |
dc.subject | Pre-trained model | - |
dc.subject | Road condition | - |
dc.subject | Traffic flow | - |
dc.subject | Traffic flow forecasting | - |
dc.subject | Traffic flow prediction | - |
dc.subject | Traffic systems | - |
dc.subject | Traffic volume prediction | - |
dc.subject | Big data | - |
dc.title | TrafficBERT: Pre-trained model with large-scale data for long-range traffic flow forecasting | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kang, S. | - |
dc.identifier.doi | 10.1016/j.eswa.2021.115738 | - |
dc.identifier.scopusid | 2-s2.0-85113591041 | - |
dc.identifier.wosid | 000705531600004 | - |
dc.identifier.bibliographicCitation | Expert Systems with Applications, v.186 | - |
dc.relation.isPartOf | Expert Systems with Applications | - |
dc.citation.title | Expert Systems with Applications | - |
dc.citation.volume | 186 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Operations Research & Management Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Operations Research & Management Science | - |
dc.subject.keywordPlus | Forecasting | - |
dc.subject.keywordPlus | Motor transportation | - |
dc.subject.keywordPlus | Recurrent neural networks | - |
dc.subject.keywordPlus | Roads and streets | - |
dc.subject.keywordPlus | Street traffic control | - |
dc.subject.keywordPlus | Autonomous driving | - |
dc.subject.keywordPlus | Bidirectional encoder representation from transformer | - |
dc.subject.keywordPlus | Large scale data | - |
dc.subject.keywordPlus | Pre-trained model | - |
dc.subject.keywordPlus | Road condition | - |
dc.subject.keywordPlus | Traffic flow | - |
dc.subject.keywordPlus | Traffic flow forecasting | - |
dc.subject.keywordPlus | Traffic flow prediction | - |
dc.subject.keywordPlus | Traffic systems | - |
dc.subject.keywordPlus | Traffic volume prediction | - |
dc.subject.keywordPlus | Big data | - |
dc.subject.keywordAuthor | BERT | - |
dc.subject.keywordAuthor | Big data | - |
dc.subject.keywordAuthor | Pre-trained model | - |
dc.subject.keywordAuthor | Traffic flow | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
94, Wausan-ro, Mapo-gu, Seoul, 04066, Korea02-320-1314
COPYRIGHT 2020 HONGIK UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.